add encoder

README.md

@@ -4,7 +4,7 @@ datasets:
 pipeline_tag: robotics
 ---
 
-This model has been trained on a larger version of the commabody dataset. It includes a vqgan gan encoder/decoder fine tuned from imagenet, as well as a GPT2 trained to predict the next frame, wheel speeds and actions. 
-It can be used either as a simulator or as a policy. 
+This model has been trained on a larger version of the commabody dataset.   
+It includes a [vqgan](https://github.com/CompVis/taming-transformers) encoder/decoder fine tuned from imagenet. It compresses images of size 250x160 to 16x10 tokens.  
 
-todo: link to blog post, link to body-jim example script, include example video
+It also includes a GPT2 model trained to predict the next frame, wheel speeds and actions. It can be used either as a simulator or as a policy.  

encoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edda6a54630d1250822cc743127d54ace177418b859e6170bc90ba4901cbe8f2
+size 119675145